WO2017214445A1 - Methods for identifying crosses for use in plant breeding - Google Patents
Methods for identifying crosses for use in plant breeding Download PDFInfo
- Publication number
- WO2017214445A1 WO2017214445A1 PCT/US2017/036626 US2017036626W WO2017214445A1 WO 2017214445 A1 WO2017214445 A1 WO 2017214445A1 US 2017036626 W US2017036626 W US 2017036626W WO 2017214445 A1 WO2017214445 A1 WO 2017214445A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- crosses
- parents
- potential
- subgroup
- target
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 111
- 238000003976 plant breeding Methods 0.000 title claims abstract description 20
- 238000009395 breeding Methods 0.000 claims abstract description 148
- 230000001488 breeding effect Effects 0.000 claims abstract description 148
- 230000002068 genetic effect Effects 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 5
- 230000001419 dependent effect Effects 0.000 claims 2
- 241000196324 Embryophyta Species 0.000 description 50
- 238000012360 testing method Methods 0.000 description 33
- 239000000047 product Substances 0.000 description 22
- 239000011159 matrix material Substances 0.000 description 16
- 230000008569 process Effects 0.000 description 16
- 240000008042 Zea mays Species 0.000 description 15
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 description 14
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 14
- 235000009973 maize Nutrition 0.000 description 14
- 230000015654 memory Effects 0.000 description 14
- 238000009826 distribution Methods 0.000 description 13
- 210000001519 tissue Anatomy 0.000 description 13
- 210000001161 mammalian embryo Anatomy 0.000 description 9
- 239000013065 commercial product Substances 0.000 description 6
- 238000007796 conventional method Methods 0.000 description 6
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000003205 genotyping method Methods 0.000 description 6
- 239000003550 marker Substances 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 241000894007 species Species 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 235000002566 Capsicum Nutrition 0.000 description 3
- 240000001980 Cucurbita pepo Species 0.000 description 3
- 235000010469 Glycine max Nutrition 0.000 description 3
- 244000068988 Glycine max Species 0.000 description 3
- 238000003556 assay Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003306 harvesting Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 108700028369 Alleles Proteins 0.000 description 2
- 244000105624 Arachis hypogaea Species 0.000 description 2
- 235000010777 Arachis hypogaea Nutrition 0.000 description 2
- 244000075850 Avena orientalis Species 0.000 description 2
- 235000007319 Avena orientalis Nutrition 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 2
- 235000011299 Brassica oleracea var botrytis Nutrition 0.000 description 2
- 240000003259 Brassica oleracea var. botrytis Species 0.000 description 2
- 235000004977 Brassica sinapistrum Nutrition 0.000 description 2
- 241000219112 Cucumis Species 0.000 description 2
- 235000015510 Cucumis melo subsp melo Nutrition 0.000 description 2
- 240000008067 Cucumis sativus Species 0.000 description 2
- 235000010799 Cucumis sativus var sativus Nutrition 0.000 description 2
- 235000009854 Cucurbita moschata Nutrition 0.000 description 2
- 235000009852 Cucurbita pepo Nutrition 0.000 description 2
- 240000004585 Dactylis glomerata Species 0.000 description 2
- 241000234643 Festuca arundinacea Species 0.000 description 2
- 244000299507 Gossypium hirsutum Species 0.000 description 2
- 240000005979 Hordeum vulgare Species 0.000 description 2
- 235000007340 Hordeum vulgare Nutrition 0.000 description 2
- 240000004658 Medicago sativa Species 0.000 description 2
- 108091028043 Nucleic acid sequence Proteins 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 240000006394 Sorghum bicolor Species 0.000 description 2
- 244000098338 Triticum aestivum Species 0.000 description 2
- 241000607479 Yersinia pestis Species 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 108020004707 nucleic acids Proteins 0.000 description 2
- 102000039446 nucleic acids Human genes 0.000 description 2
- 150000007523 nucleic acids Chemical class 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008121 plant development Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 235000013311 vegetables Nutrition 0.000 description 2
- 240000004507 Abelmoschus esculentus Species 0.000 description 1
- 241001133760 Acoelorraphe Species 0.000 description 1
- 240000007241 Agrostis stolonifera Species 0.000 description 1
- 235000005254 Allium ampeloprasum Nutrition 0.000 description 1
- 240000006108 Allium ampeloprasum Species 0.000 description 1
- 244000291564 Allium cepa Species 0.000 description 1
- 235000002732 Allium cepa var. cepa Nutrition 0.000 description 1
- 241000219194 Arabidopsis Species 0.000 description 1
- 235000017060 Arachis glabrata Nutrition 0.000 description 1
- 235000018262 Arachis monticola Nutrition 0.000 description 1
- 235000000832 Ayote Nutrition 0.000 description 1
- 241000219310 Beta vulgaris subsp. vulgaris Species 0.000 description 1
- 235000011331 Brassica Nutrition 0.000 description 1
- 241000219198 Brassica Species 0.000 description 1
- 235000014698 Brassica juncea var multisecta Nutrition 0.000 description 1
- 240000002791 Brassica napus Species 0.000 description 1
- 235000006008 Brassica napus var napus Nutrition 0.000 description 1
- 240000007124 Brassica oleracea Species 0.000 description 1
- 235000003899 Brassica oleracea var acephala Nutrition 0.000 description 1
- 235000011301 Brassica oleracea var capitata Nutrition 0.000 description 1
- 235000017647 Brassica oleracea var italica Nutrition 0.000 description 1
- 235000001169 Brassica oleracea var oleracea Nutrition 0.000 description 1
- 235000010149 Brassica rapa subsp chinensis Nutrition 0.000 description 1
- 235000006618 Brassica rapa subsp oleifera Nutrition 0.000 description 1
- 235000000536 Brassica rapa subsp pekinensis Nutrition 0.000 description 1
- 241000499436 Brassica rapa subsp. pekinensis Species 0.000 description 1
- 244000188595 Brassica sinapistrum Species 0.000 description 1
- 244000025254 Cannabis sativa Species 0.000 description 1
- 240000008574 Capsicum frutescens Species 0.000 description 1
- 244000241235 Citrullus lanatus Species 0.000 description 1
- 235000012828 Citrullus lanatus var citroides Nutrition 0.000 description 1
- 241000207199 Citrus Species 0.000 description 1
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 1
- 235000005979 Citrus limon Nutrition 0.000 description 1
- 244000131522 Citrus pyriformis Species 0.000 description 1
- 240000000560 Citrus x paradisi Species 0.000 description 1
- 235000013162 Cocos nucifera Nutrition 0.000 description 1
- 244000060011 Cocos nucifera Species 0.000 description 1
- 240000007154 Coffea arabica Species 0.000 description 1
- 229920000742 Cotton Polymers 0.000 description 1
- 235000009804 Cucurbita pepo subsp pepo Nutrition 0.000 description 1
- 235000002767 Daucus carota Nutrition 0.000 description 1
- 244000000626 Daucus carota Species 0.000 description 1
- 208000035240 Disease Resistance Diseases 0.000 description 1
- 244000166124 Eucalyptus globulus Species 0.000 description 1
- 240000006927 Foeniculum vulgare Species 0.000 description 1
- 235000004204 Foeniculum vulgare Nutrition 0.000 description 1
- 241000204888 Geobacter sp. Species 0.000 description 1
- 235000004341 Gossypium herbaceum Nutrition 0.000 description 1
- 240000002024 Gossypium herbaceum Species 0.000 description 1
- 235000009432 Gossypium hirsutum Nutrition 0.000 description 1
- 244000020551 Helianthus annuus Species 0.000 description 1
- 235000003222 Helianthus annuus Nutrition 0.000 description 1
- 235000003228 Lactuca sativa Nutrition 0.000 description 1
- 240000008415 Lactuca sativa Species 0.000 description 1
- 235000004431 Linum usitatissimum Nutrition 0.000 description 1
- 240000006240 Linum usitatissimum Species 0.000 description 1
- 241000208682 Liquidambar Species 0.000 description 1
- 235000006552 Liquidambar styraciflua Nutrition 0.000 description 1
- 235000007688 Lycopersicon esculentum Nutrition 0.000 description 1
- 241000220225 Malus Species 0.000 description 1
- 235000010624 Medicago sativa Nutrition 0.000 description 1
- 235000017587 Medicago sativa ssp. sativa Nutrition 0.000 description 1
- 241000243785 Meloidogyne javanica Species 0.000 description 1
- 240000005561 Musa balbisiana Species 0.000 description 1
- 235000018290 Musa x paradisiaca Nutrition 0.000 description 1
- 208000000291 Nematode infections Diseases 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 244000061176 Nicotiana tabacum Species 0.000 description 1
- 240000007817 Olea europaea Species 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 235000006990 Pimenta dioica Nutrition 0.000 description 1
- 240000008474 Pimenta dioica Species 0.000 description 1
- 241001236219 Pinus echinata Species 0.000 description 1
- 235000005018 Pinus echinata Nutrition 0.000 description 1
- 235000017339 Pinus palustris Nutrition 0.000 description 1
- 241000218621 Pinus radiata Species 0.000 description 1
- 235000008577 Pinus radiata Nutrition 0.000 description 1
- 241000722363 Piper Species 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 240000003889 Piper guineense Species 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 241000758706 Piperaceae Species 0.000 description 1
- 240000004713 Pisum sativum Species 0.000 description 1
- 235000010582 Pisum sativum Nutrition 0.000 description 1
- 241000209049 Poa pratensis Species 0.000 description 1
- 208000020584 Polyploidy Diseases 0.000 description 1
- 241000219000 Populus Species 0.000 description 1
- 238000012356 Product development Methods 0.000 description 1
- 244000184734 Pyrus japonica Species 0.000 description 1
- 244000088415 Raphanus sativus Species 0.000 description 1
- 235000006140 Raphanus sativus var sativus Nutrition 0.000 description 1
- 240000000528 Ricinus communis Species 0.000 description 1
- 235000004443 Ricinus communis Nutrition 0.000 description 1
- 241000209051 Saccharum Species 0.000 description 1
- 240000000111 Saccharum officinarum Species 0.000 description 1
- 235000007201 Saccharum officinarum Nutrition 0.000 description 1
- 240000003768 Solanum lycopersicum Species 0.000 description 1
- 235000002597 Solanum melongena Nutrition 0.000 description 1
- 244000061458 Solanum melongena Species 0.000 description 1
- 235000007230 Sorghum bicolor Nutrition 0.000 description 1
- 235000011684 Sorghum saccharatum Nutrition 0.000 description 1
- 235000009337 Spinacia oleracea Nutrition 0.000 description 1
- 244000300264 Spinacia oleracea Species 0.000 description 1
- 241000044578 Stenotaphrum secundatum Species 0.000 description 1
- 235000021536 Sugar beet Nutrition 0.000 description 1
- 244000269722 Thea sinensis Species 0.000 description 1
- 235000011941 Tilia x europaea Nutrition 0.000 description 1
- 240000006909 Tilia x europaea Species 0.000 description 1
- 108700019146 Transgenes Proteins 0.000 description 1
- 241000219793 Trifolium Species 0.000 description 1
- 208000026487 Triploidy Diseases 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 235000007244 Zea mays Nutrition 0.000 description 1
- FJJCIZWZNKZHII-UHFFFAOYSA-N [4,6-bis(cyanoamino)-1,3,5-triazin-2-yl]cyanamide Chemical compound N#CNC1=NC(NC#N)=NC(NC#N)=N1 FJJCIZWZNKZHII-UHFFFAOYSA-N 0.000 description 1
- 229930002877 anthocyanin Natural products 0.000 description 1
- 235000010208 anthocyanin Nutrition 0.000 description 1
- 239000004410 anthocyanin Substances 0.000 description 1
- 150000004636 anthocyanins Chemical class 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000001390 capsicum minimum Substances 0.000 description 1
- 235000014633 carbohydrates Nutrition 0.000 description 1
- 150000001720 carbohydrates Chemical class 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 235000020971 citrus fruits Nutrition 0.000 description 1
- 235000016213 coffee Nutrition 0.000 description 1
- 235000013353 coffee beverage Nutrition 0.000 description 1
- 235000009508 confectionery Nutrition 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 235000005489 dwarf bean Nutrition 0.000 description 1
- 244000013123 dwarf bean Species 0.000 description 1
- 210000002257 embryonic structure Anatomy 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 235000004426 flaxseed Nutrition 0.000 description 1
- -1 for example Substances 0.000 description 1
- 239000003205 fragrance Substances 0.000 description 1
- 238000012252 genetic analysis Methods 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 102000054766 genetic haplotypes Human genes 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000004571 lime Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000003147 molecular marker Substances 0.000 description 1
- 239000002773 nucleotide Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 235000020232 peanut Nutrition 0.000 description 1
- YEHCICAEULNIGD-MZMPZRCHSA-N pergolide Chemical compound C1=CC([C@H]2C[C@@H](CSC)CN([C@@H]2C2)CCC)=C3C2=CNC3=C1 YEHCICAEULNIGD-MZMPZRCHSA-N 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 235000015136 pumpkin Nutrition 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000009394 selective breeding Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 235000020354 squash Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 235000013616 tea Nutrition 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 239000003053 toxin Substances 0.000 description 1
- 231100000765 toxin Toxicity 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01H—NEW PLANTS OR NON-TRANSGENIC PROCESSES FOR OBTAINING THEM; PLANT REPRODUCTION BY TISSUE CULTURE TECHNIQUES
- A01H1/00—Processes for modifying genotypes ; Plants characterised by associated natural traits
- A01H1/04—Processes of selection involving genotypic or phenotypic markers; Methods of using phenotypic markers for selection
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01H—NEW PLANTS OR NON-TRANSGENIC PROCESSES FOR OBTAINING THEM; PLANT REPRODUCTION BY TISSUE CULTURE TECHNIQUES
- A01H1/00—Processes for modifying genotypes ; Plants characterised by associated natural traits
- A01H1/02—Methods or apparatus for hybridisation; Artificial pollination ; Fertility
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Definitions
- the present disclosure generally relates to methods for use in plant breeding and in related breeding programs, and in particular to methods for use in identifying parents for creating new crosses for use in plant breeding and in related plant breeding programs.
- FIG. 1 is a block diagram of an exemplary system of the present disclosure suitable for identifying plant crosses for use in plant breeding;
- FIG. 2 is a block diagram of a computing device that may be used in the exemplary system of FIG. 1;
- FIGS. 3 A-3F illustrate an excerpt of an exemplary crosses data structure suitable for use with the system of FIG. 1;
- FIG. 4 is an exemplary method, suitable for use with the system of FIG. 1, for identifying plant crosses for use in plant breeding;
- FIG. 5 is a graphical representation of clustering of parents for potential crosses
- FIG. 6 is another graphical representation of an exemplary distribution of parental usage in certain breeding populations
- FIG. 7 is a graphical representation of a hypothetical distribution of parental usage in breeding populations in certain breeding systems
- FIG. 8 illustrates an exemplary breeding situation involving selection from among four potential parents.
- FIG. 9 is an exemplary graphical comparison of example inbred usage indexes (IUIs), based on historical data (as found in a crosses data structure for certain years), for conventional breeding and the exemplary method of FIG. 4.
- IUIs inbred usage indexes
- the systems and methods herein are configured to select parents for use in breeding pipelines based on predicted commercial value of potential crosses between the parents, as determined from commercial success of the parents (and/or the parents' parents, and/or other members in the parental lines) in combination with relatedness and/or risks associated with the given crosses, and further relying on individual traits and/or characteristics of the parents (and/or the parents' parents, and/or other members in the parental lines). In this manner, a more complete picture of the potential crosses of the parents is provided, from which efficiency in selecting populations of crosses for the plant breeding pipelines can be gained.
- FIG. 1 illustrates an exemplary system 100 for identifying crosses for use in breeding plants, in which the one or more aspect of the present disclosure may be implemented.
- parts of the system 100 are presented in one arrangement, other embodiments may include the same or different parts arranged otherwise depending, for example, on particular plants being bred, particular characteristics and/or traits of interest, particular breeding techniques implemented, etc.
- the system 100 generally includes a breeding pipeline 102, which is provided to create new plants by crossing an existing pool of parents.
- the breeding pipeline 102 is employed to create commercial products by first crossing parent plants to produce offspring seed (and/or plants).
- the pipeline 102 generally defines a pyramidal progression, whereby it starts with a large number of potential crosses from parents, and keeps narrowing down to pick preferred and/or desired ones of the crosses.
- the pipeline 102 often involves identification of preferred performing populations from this large number of potential crosses, which typically involves subjecting the populations of offspring to rigorous testing using a wide range of methods known in the art.
- this process may involve testing hundreds, thousands, or more crosses in multiple phases at several locations, over several years, to arrive at a reduced set of crosses selected for commercial product development.
- the breeding pipeline 102 comprises many processes designed to reduce a large number of crosses down to a relatively few number of superior-performing commercial products.
- the breeding pipeline 102 is described with reference to, and is generally directed to, maize.
- the methods disclosed herein are not limited to maize and may be employed in a plant breeding pipeline/program relating to other plants, for example, to improve any fruit, vegetable, grass, tree, or ornamental crop, including, but not limited to, maize (Zea mays), soybean (Glycine max), cotton (Gossypium hirsutum), peanut (Arachis hypogaea), barley (Hordeum vulgare), oats (Avena sativa), orchard grass (Dactylis glomerata), rice (Oryza sativa, including indica and japonica varieties), sorghum (Sorghum bicolor), sugar cane (Saccharum sp), tall fescue (Festuca arundinacea), turfgrass species (e.g., species: Agrostis stolonifera, Poa
- the breeding pipeline 102 includes a parent selection and crossing phase 104 and a testing and selection phase 106, which together yield one or more commercial products 108 (broadly, selected crosses).
- the pipeline 102 includes a variety of conventional processes known to those skilled in the art, as described below, used in the different phases 104, 106 to ultimately achieve the commercial products 108.
- the illustrated system 100 includes a breeding engine 1 12 uniquely configured, in connection with crosses data structure 1 14, to make and provide the selection of parents to the breeding pipeline 102, and in particular to the parent selection and crossing phase 104 thereof (thereby facilitating an improved likelihood of providing successful commercial products 108, and potentially utilizing fewer parents/crosses in phase 104 than in traditional operations).
- the parents are actually crossed (still in phase 104) to derive a plant (e.g., a seed) from the specified parents.
- a plant e.g., a seed
- any convention methods of crossing plants may be employed to actually create the population of plants, once the parents have been selected as described herein.
- those skilled in the art would understand that various different types of fertilization between two parents may be employed herein, often depending on the types of parents selected, to create a plant.
- phase 104 of the pipeline 102 the testing and selection phase 106, which includes a growing space, such as, for example, a greenhouse, a nursery, a breeding plot, a field, etc.
- a growing space such as, for example, a greenhouse, a nursery, a breeding plot, a field, etc.
- the plants are derived from the crosses (in phase 104), based on one or more conventional methods (as described above), the plants are planted in, or more generally subject to, the growing space in phase 106, whereupon the plants are grown.
- the crosses may be subjected to any number of tests.
- the tests are generally employed to determine which of the crosses in the population should be advanced for subsequent testing/evaluation (as part of the testing and selection phase 106) and/or which should be advanced as a commercial product 108, where such selections/advancements are made depending on various criterion including (but not limited to) resistance to certain diseases, resistance to certain pests, visual inspection, cost of goods associated with the crosses, propensity of the crosses to produce haploid offspring, propensity of the crosses to product double haploid offspring, propensity of the crosses for induction, and/or propensity of the crosses to have a number of chromosomes in at least one of their cells to be doubled.
- the crosses are tested for the presence of at least one trait via one or more techniques known in the art of plant breeding.
- Such techniques may include any number of tests, trials, or analyses known to be useful for evaluating plant performance, including any phenotyping or genotyping assays known in the art.
- seed phenotypes which may be evaluated, include size, shape, surface area, volume, mass, and/or quantity of chemicals in at least one tissue of the seed, for example, anthocyanins, proteins, lipids, carbohydrates, etc. in the embryo, endosperm or other seed tissues.
- a plant e.g., cultivated from a seed, etc.
- a particular chemical e.g., a pharmaceutical, a toxin, a fragrance, etc.
- the seed can be assayed to quantify the desired chemical. Based on the results of such test(s), a breeder or other user may then select for advancement in the pipeline 102 those seeds or population(s) of seeds that appear to contain one or more desired traits.
- Examples of genetic analyses may include any form of nucleic acid detection and/or characterization, including sequencing, genotyping by sequencing, detection and characterization of sequences associated with certain alleles and/or quantitative trait loci, allele frequencies in a population of seeds, transgene, or RNA sequences in that a user is interested, etc.
- tissue of the crosses may also be genotyped using any methods useful to breeders (as opposed to testing the entire seed or plant). Common examples include harvesting samples of embryo and/or endosperm material/tissue in a way that does not kill or otherwise prevent the seeds or plants from surviving the ordeal. For example, seed chipping may be employed to obtain seed samples from the crosses for use in determining whether a specific sequence of nucleic acid is contained within the seed and/or, potentially, within a population from which the sampled seed was derived.
- any other methods of harvesting samples of tissue of the seeds for analysis can be used for the purposes of genotyping, as well as conducting genotyping assays directly on the tissue of the seeds that do not require samples of tissue to be removed.
- the embryo and/or endosperm remain connected to other tissue of the seeds.
- the embryo and/or endosperm are separated from other tissue of the seeds (e.g., embryo rescue, embryo excision, etc.).
- the tissue of the seeds (or plants) may be accessed via one or more of a wide range of methods to genotype the crosses.
- Commonly used methods include, for example, using at least one molecular marker (e.g., a single-nucleotide polymorphism (S P) marker, etc.) and/or at least one sequencing-based method (e.g., genotype by sequencing (GBS), etc.) to detect the presence of certain nucleotide sequences in the embryo or endosperm of the seeds or plants.
- at least one molecular marker e.g., a single-nucleotide polymorphism (S P) marker, etc.
- GGS genotype by sequencing
- nucleotide sequences in plant embryo or endosperm tissue of the seeds could be employed in conjunction with the methods described herein, depending on circumstances (e.g. species of plants, number of plants to genotype, size of breeding program, etc.).
- any genotyping method or phenotyping method that a user employs to aid in the process of selecting seeds or plants (or embryos, or endosperms) for advancement to a next stage in the testing and selection phase 106, and/or in the breeding pipeline 102, may be used.
- the testing and selection phase 106 of the breeding pipeline 102 in the illustrated embodiment is not limited to certain or particular genotyping or phenotyping methods or technologies when assaying the crosses (and/or tissues on and/or within crosses), as any method and/or technology suitable to aid in the determination of a genotype and/or phenotype of the crosses' cells at any stage of the life cycle may be used.
- a plant researcher may germinate a seed from a cross and/or cultivate the plant from an embryo to some later development stage in order to complete a test useful for making selections on the plant.
- the testing and selection phase 106 of the breeding pipeline 102 may also include multiple iterations, as indicated by the arrows in FIG. 1, in which crosses are grown and/or testing and selections are made, and whereby the population of potential crosses is reduced.
- the testing performed at different parts of the testing and selection phase 106 may be modified between different ones of such iterations, to reduce the population of crosses based on any desirable criteria. What' s more, further modification of the population of crosses may be completed as part of the testing and selection phase 106, where different traits are added to the crosses, such as, for example, resistance to one or more pests, diseases, etc.
- seeds or populations of seeds are advanced to become commercial products 108.
- the seeds and/or crosses are then generally bulked to provide seeds to be sold
- the breeding engine 112 of the system 100 is configured, by computer-executable instructions, to select crosses to provide to the breeding pipeline 102 (specifically, to the parent selection and crossing phase 104) for use therein as described above. For example, once provided to the parent selection and crossing phase 104, the selected/identified parents (as provided by the breeding engine 112) are actually crossed (at phase 104).
- the breeding engine 112 is configured to access the crosses data structure 114 and, based on data therein, generate a population prediction score for each of the crosses in the data structure 114 (specifically, based on data in the crosses data structure 114 associated with the parents to be crossed). The breeding engine 112 is configured to then generate and/or retrieve, from the data structure 114, population prediction scores for select ones (or all) of the crosses in the population.
- the breeding engine 112 is configured to select (e.g., filter, etc.) a subgroup of the crosses based on a threshold associated with the population prediction scores, and to further select (e.g., filter, etc.) a pool of target crosses from the subgroup based on the relatedness of the parents within the subgroup (e.g., to help achieve a generally manageable number of potential crosses for implementation in the breeding pipeline 102, etc.).
- the breeding engine 112 is configured to discard (i.e., not select for advancement in the pipeline 102) parents from the pool of target crosses (and thus remove undesired crosses coming from these parents) that contain undesired traits based on a set of one or more predetermined rules and associated thresholds (as defined by the rules). Any number of rules and thresholds may be applied in connection with discarding the unwanted/undesired crosses (and, thus, their parents) (e.g., ten rules, less than ten rules, eighteen rules or less, twenty rules or less, more than twenty rules, any other number of rules, etc.).
- the rules and associated thresholds may be stored in the crosses data structure 114, or they may be stored separately in memory associated with the breeding engine 112.
- rules and thresholds may be generated by breeders (or other users of the system 100), as desired, and/or may be based on historical data (e.g., historical data included in the data structure 114, other historical data, etc.).
- historical data e.g., historical data included in the data structure 114, other historical data, etc.
- Table 1 illustrates five example rules and corresponding thresholds that may be used by the breeding engine 112 in connection with filtering out, or culling, parents (or crosses) from a pool of target crosses (or target parents), based on undesired phenotype traits and/or characteristics.
- the rules in Table 1 relate to stalk lodging (STLP), root lodging (RTLP), Goss Wilt (GW), parental similarity (SIMILARITY), and the difference between the expected relative maturity (ERM) between the two parents (i.e., dERM).
- the breeding engine 112 is configured to then select at least one cross from the pool of remaining crosses (i.e., select two parents from the pool to cross), based on potential to produce commercial offspring as well as on populating the breeding pipeline 102 with a diverse pool of lines.
- Populating the breeding pipeline 102 with a diverse pool of lines may include one or more of choosing parents to cross that show resistance to several diseases, choosing parents to cross that are tested in the pipeline 102 for several years, and directing the pipeline 102 to include a desired product portfolio to meet current and/or predicted market needs.
- the breeding engine 112 is configured to direct the selected ones of the parents (or the selected crosses) to the breeding pipeline 102 to actually be crossed.
- the data related to the parents and/or the crosses of parents is compiled into the crosses data structure 1 14 from the breeding pipeline 102 (as indicated by the dotted lines in FIG. 1).
- the data structure 1 14 includes historical data 1 16 for years 1-N, for desired seeds, plants, etc. (e.g., maize in the various examples herein, etc.).
- the data structure 114 includes data for multiple different seed parents and various example metrics, characteristics and/or traits, etc. associated therewith, as well as with the potential crosses thereof, for use by the breeding engine 1 12.
- the data structure 1 14 may include data related to tassel skeletonization in the offspring of a particular maize inbred.
- the data structure 1 14 may include data related to the occurrence of tolerance to root knot nematode infection in the offspring of a particular soybean or cotton plant. Similarly, the data structure 1 14 may include data related to other characteristics of maize, or other characteristics of other crops.
- FIG. 2 illustrates an exemplary computing device 200 that may be used in the system 100, for example, in connection with various phases of the breeding pipeline 102, in connection with the breeding engine 1 12, the crosses data structure 1 14, etc.
- breeders or other users interact with computing devices, consistent with computing device 200, to enter data and/or to access data in the crosses data structure 1 14 to support breeding decisions and/or testing completed/accomplished by such breeders or other users.
- the breeding engine 1 12 includes at least one computing device consistent with computing device 200.
- the computing device 200 may be configured, by executable instructions, to implement the various algorithms and other operations described herein.
- the system 100 as described herein, may include a variety of different computing devices, either consistent with computing device 200 or different from computing device 200.
- the exemplary computing device 200 may include, for example, one or more servers, workstations, personal computers, laptops, tablets, smartphones, other suitable computing devices, combinations thereof, etc.
- the computing device 200 may include a single computing device, or it may include multiple computing devices located in close proximity or distributed over a geographic region, and coupled to one another via one or more networks.
- networks may include, without limitations, the Internet, an intranet, a private or public local area network (LAN), wide area network (WAN), mobile network,
- the crosses data structure 1 14 of the system 100 includes at least one server computing device, while the breeding engine 1 12 includes at least one separate computing device, which is coupled to the crosses data structure 1 14, directly and/or by one or more LANs, etc.
- the illustrated computing device 200 includes a processor 202 and a memory 204 that is coupled to (and in communication with) the processor 202.
- the processor 202 may include, without limitation, one or more processing units (e.g., in a multi-core configuration, etc.), including a central processing unit (CPU), a microcontroller, a reduced instruction set computer (RISC) processor, an application specific integrated circuit (ASIC), a programmable logic device (PLD), a gate array, and/or any other circuit or processor capable of the functions described herein.
- CPU central processing unit
- RISC reduced instruction set computer
- ASIC application specific integrated circuit
- PLD programmable logic device
- gate array any other circuit or processor capable of the functions described herein.
- the memory 204 is one or more devices that enable information, such as executable instructions and/or other data, to be stored and retrieved.
- the memory 204 may include one or more computer-readable storage media, such as, without limitation, dynamic random access memory (DRAM), static random access memory (SRAM), read only memory (ROM), erasable programmable read only memory (EPROM), solid state devices, flash drives, CD-ROMs, thumb drives, tapes, hard disks, and/or any other type of volatile or nonvolatile physical or tangible computer-readable media.
- DRAM dynamic random access memory
- SRAM static random access memory
- ROM read only memory
- EPROM erasable programmable read only memory
- solid state devices solid state devices
- flash drives CD-ROMs, thumb drives, tapes, hard disks, and/or any other type of volatile or nonvolatile physical or tangible computer-readable media.
- the memory 204 may be configured to store, without limitation, the crosses data structure 1 14, parent and/or cross selection/cull rules, various thresholds as used herein, various scores as used herein, breeding decisions, data related to commercial products, and/or other types of data (and/or data structures) suitable for use as described herein, etc.
- computer-executable instructions may be stored in the memory 204 for execution by the processor 202 to cause the processor 202 to perform one or more of the functions described herein, such that the memory 204 is a physical, tangible, and non-transitory computer-readable storage media. It should be appreciated that the memory 204 may include a variety of different memories, each implemented in one or more of the functions or processes described herein.
- the computing device 200 also includes a presentation unit 206 that is coupled to (and is in communication with) the processor 202.
- the presentation unit 206 outputs, or presents, to a user of the computing device 200 (e.g., a breeder, etc.) by, for example, displaying and/or otherwise outputting information such as, but not limited to, selected parents for use in a cross, selected crosses to advance as commercial products, and/or any other type of data.
- the presentation unit 206 may comprise a display device such that various interfaces (e.g., applications (network-based or otherwise), etc.) may be displayed at computing device 200, and in particular at the display device, to display such information and data, etc.
- the computing device 200 may cause the interfaces to be displayed at a display device of another computing device, including, for example, a server hosting a website having multiple webpages, or interacting with a web application employed at the other computing device, etc.
- Presentation unit 206 may include, without limitation, a liquid crystal display (LCD), a light- emitting diode (LED) display, an organic LED (OLED) display, an "electronic ink” display, combinations thereof, etc.
- the presentation unit 206 may include multiple units.
- the computing device 200 further includes an input device 208 that receives input from the user.
- the input device 208 is coupled to (and is in communication with) the processor 202 and may include, for example, a keyboard, a pointing device, a mouse, a stylus, a touch sensitive panel (e.g., a touch pad or a touch screen, etc.), another computing device, and/or an audio input device.
- a touch screen such as that included in a tablet or similar device, may perform as both the presentation unit 206 and the input device 208.
- the presentation unit 206 and the input device 208 may be omitted.
- the illustrated computing device 200 includes a network interface 210 coupled to (and in communication with) the processor 202 (and, in some embodiments, to the memory 204 as well).
- the network interface 210 may include, without limitation, a wired network adapter, a wireless network adapter, a telecommunications adapter, or other device capable of communicating to one or more different networks.
- the network interface 210 is employed to receive inputs to the computing device 200.
- the network interface 210 may be coupled to (and in communication with) in-field data collection devices, such as those described in PCT Application No.
- the computing device 200 includes the processor 202 and one or more network interfaces incorporated into or with the processor 202.
- the breeding engine 1 12 may be configured to provide (e.g., generate and cause to be displayed at a computing device of a breeder) and/or respond to a user interface, through which a breeder (broadly, a user) is able to make selections and provide inputs regarding parents and crosses.
- the user interface may be provided directly at a computing device (e.g., computing device 200, etc.) of the breeder, in which the breeding engine 1 12 is employed, or via one or more network-based applications through which a remote user (again, potentially a breeder) may be able to interact with the breeding engine 1 12 as described herein.
- FIGS. 3 A-3F illustrate an exemplary excerpt 300, which forms part of the crosses data structure 1 14 of the system 100.
- the data contained in the excerpt 300 is stored in memory (e.g., memory 204, etc.), and accessed by the breeding engine 1 12 to perform the operations as described herein.
- the illustrated excerpt 300 generally includes a table identifying multiple different crosses for maize, along with the parents PI, P2 of each of the different crosses (FIG. 3 A), and various example metrics, characteristics and/or traits associated with the crosses and/or the parents PI, P2 (FIGS. 3A-3F).
- the excerpt 300 includes example metrics, characteristics and/or traits such as, and without limitation, linear unbiased predictors of selection indexes of parents
- PI SELIN blup, P2_SELIN_blup best linear unbiased predictors of yield of the parents (P 1 YLD BE blup, P2_YLD_BE_blup), moisture content of the parents (Pl MST blup, P2_MST_blup), selection test mean of the parents (PI SELTM blup, P2_SELTM_blup), test weights of the parents (Pl_TWT_blup,P2_TWT_blup), and root lodging of the parents
- FIG. 3B illustrates various metrics that may be used herein, such as probability that a parent tested in a stage can advance to a next stage (Pl AVG SCORE PS l, P2 AVG SCORE PS 1, PI PR AD V, P2 PR ADV). These metrics are obtained from machine learning models that are trained to predict a probability of the parent in the identified cross advancing each stage of the breeding pipeline.
- excerpt 300 is exemplary in nature and is provided herein for purposes of illustration only. Those skilled in the art will readily understand that additional and/or different data may be included related to various metrics, characteristics and/or traits of the crosses and/or their parents PI, P2. Further, the excerpt 300 may include additional and/or different metrics, for example, scores, ranges, thresholds, and/or other mechanisms, etc., by which the crosses may be identified and/or (un)selected, in the systems and methods described herein.
- FIG. 4 illustrates an exemplary method 400 of selecting crosses of certain parents in a plant breeding process.
- the exemplary method 400 is described herein in connection with the system 100, and may be implemented in the breeding engine 1 12 of the system 100. Further, for purposes of illustration, the exemplary method 400 is also described with reference to the computing device 200 of FIG. 2 and the excerpt 300 of FIGS. 3A-3F from the crosses data structure 1 14 of the system 100.
- the method 400, or other methods described herein are not limited to the system 100, the computing device 200, or the excerpt 300.
- the systems, data structures, and the computing devices described herein are not limited to the exemplary method 400.
- a breeder (or other user) initially identifies a desired plant type for breeding, potentially consistent with one or more desired characteristics and/or traits to be advanced, or a desired performance. For example, for a region in the central, southern United States, a breeder whose objective is maize may select to breed drought resistant maize that is not susceptible to Goss Wilt disease, and that also meets a predefined diversity criterion (e.g., to help maintain integrity of the breeding program, etc.). Once identified, the breeder provides one or more inputs to the breeding engine 1 12 (e.g., via computing device 200 using a network-based application or other application, etc.) consistent with the desired plant type and/or desired characteristics and/or traits.
- the breeding engine 1 12 e.g., via computing device 200 using a network-based application or other application, etc.
- the inputs that the breeder provides may include an input identifying maize as the desired plant along with three weight inputs that define the relative importance of the drought resistance characteristic, the Goss Wilt resistance characteristic, and the diversity requirement.
- the breeding engine 1 12 accesses, at 402, the crosses data structure 1 14 and initially identifies potential parents for breeding (based on the inputs), thereby resulting in identification of a set of potential crosses.
- the parents (and crosses) within the data structure 1 14 may be limited in one or more high-level manners consistent with one or more user inputs from the breeder, including, for example, selection of parents (and crosses) consistent with the particular plant type indicated (e.g., maize, etc.), the predicted performance (e.g., yield, etc.), the region of intended growing (e.g., central, southern United States; etc.), growing environments (e.g., arid, etc.), market needs in the intended region of growing, certain genotype or phenotype characteristics (e.g., tolerances to disease and/or stress such as drought, traits that make crosses cost-effective to commercialize and/or produce on an industrial scale, etc.), the desired product portfolio in the desired region of breeding, or any other trait, characteristic, or outcome potentially input (or otherwise desired) by the breeder.
- plant type indicated e.g., maize, etc.
- the predicted performance e.g., yield, etc.
- the region of intended growing e.g., central, southern
- the breeding engine 1 12 Upon accessing the data structure 1 14, and initially identifying potential parents/crosses based on the breeder's preliminary inputs, the breeding engine 1 12 generates, at 404, a population prediction score for selected crosses involving the selected potential parents.
- the population prediction score may be generated for the identified crosses, by the breeding engine 1 12, each time the breeding engine 1 12 selects or identifies them for possible use in the plant breeding pipeline 102 (consistent with FIG. 4).
- the population prediction score may alternatively be generated intermittently (e.g., periodically, or at one or more regular or irregular intervals, etc.), by the breeding engine 1 12 (e.g., as an update based on new data provided to the crosses data structure 1 14, etc.), and stored in the crosses data structure 1 14 to limit regeneration upon subsequent use of the score by the breeding engine 1 12.
- the population prediction score is generally a prediction of commercial success for each of the selected crosses.
- Commercial success may be defined by any desired metric of performance. Common examples of commercial success for a cross include being selected for advancement to some point in the breeding system 100, whereby the cross is "coded" for commercialization and/or the cross is actually released as a commercial product. Additionally, or alternatively, commercial success may represent a cross' s performance as a commercial product (e.g., a certain number of units of the product were sold on the market, a number of years the cross is in the market, etc.).
- the breeding engine 112 employs one or more different supervised, unsupervised, or semi-supervised algorithms/models such as, but not limited to, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems algorithms ⁇ See “Machine learning: a probabilistic perspective" by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to determine the population prediction score for each of the selected crosses (and thereby estimate commercial success).
- supervised, unsupervised, or semi-supervised algorithms/models such as, but not limited to, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems algorithms ⁇ See "Machine learning: a probabilistic perspective" by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety
- the scores generated by various methods can then be combined using methods such as, but not limited to, bagging and boosting, blending, ensemble methods, Bayesian model combination (BMC), simple averaging, weighted averaging, etc. See, e.g., “Ensemble Methods in Data Mining: Improving Accuracy Through Combining Predictions,” Giovanni Seni and John Elder, 2010 (Morgan and Claypool Publishers); “Popular ensemble methods: An empirical study,” Opitz & Maclin (1999), Journal of Artificial Intelligence Research 11 : 169-98; and “Ensemble-based classifiers,” Rokach (2010), Artificial Intelligence Review 33 (1-2): 1-39 (each of which is incorporated herein by reference it its entirety).
- BMC Bayesian model combination
- the breeding engine 112 may use a variation of BMC represented by Equation (1) to generate population prediction scores for potential crosses.
- the score includes a weighting applied to each of the classifiers/features used in Equation (1), and the weights, in some embodiments, reflect some aspect of the data characterizing the parents and/or their offspring.
- Equation (1) may be constructed using historical data associated with the parents of the potential crosses in the crosses data structure 114, and may be accessed by the breeding engine 112 from within the data structure 114 as needed.
- p(s i ⁇ x i , D) ⁇ 1 p(s i ⁇ x i , m, D)p m ⁇ D) (1)
- Equation (1) represents success (or failure) of the new crosses being predicted herein.
- x it D) generally represents probability that the cross will be a success.
- x corresponds to the features of the given cross that are being predicted (see further discussion below regarding such features)
- D refers to historical data being used to train the given models (and which contains both features and advancement information of the cross in the associated pipeline)
- m refers to the classifier model itself.
- the breeding engine 112 may employ, for each of the identified crosses coming from parents PI, P2, the following features (among others) in generating the population prediction scores for the potential crosses: BLUP (best linear unbiased prediction) general combining ability (PI BlupModel, P2_BlupModel) in columns Y-Z of FIG. 3C, marker based genetic similarity (Similarity) in column T of FIG. 3B, and performance in the pre- commercial pipeline (columns P-S of FIG. 3B) and some form of genetic data (e.g., marker data or haplotype data).
- the resulting population prediction scores, for each of the crosses, are then included in the excerpt 300 in columns X-Z of FIG. 3C and in columns II-MM of FIG. 3D.
- a final prediction score i.e., "advScore" (computed using Equation (1)) is included in column NN of FIG. 3D.
- This final prediction score generally combines each of the intermediate population prediction scores.
- the predicted advancement probability for the parents, PI, P2 are included in columns R-S of FIG. 3B.
- the breeding engine 112 may evaluate performance of the method(s) and select, if necessary, the one that provides best performance for a given crop and/or a given region, for example.
- historical data may be collected and then partitioned into training and test sets for each of the methods.
- Models are then built, based on the different methods, using the training data to predict the commercial success using several features for various traits, and using the historical advancement/success of the parents in the breeding pipeline 102. Once the models are built, the commercial success of the test data is predicted through the models and compared to the actual commercial success for the crosses, to determine the accuracy of the models (e.g., for each of the different methods, etc.).
- the breeding engine 112 next selects, at 406, a sub-group of the crosses, based on a threshold associated with the population prediction scores.
- a threshold of the top 40% may be employed, which is determined from historical data to capture 80% of commercial products in prior years and specific to the geographic region for the commercial products.
- the parents with the top 40% population prediction scores from the population may be selected.
- the 40% threshold may be different in other embodiments, for example, to adjust a number of potential crosses in the subgroup while maintaining a desired number of commercially successful crosses (when verified against historical data), etc.
- thresholds may include, without limitation, 10%, 15%, 20%, 25%, 31%, etc., which may correspond to capturing 60%, 70%, 74%, etc. of the commercially successful crosses, historically. It should be appreciated that other thresholds may be selected (by the breeder) based on a variety of other factors including, for example, performance of an algorithm used, a confidence in the algorithm, a number of potential crosses at start, etc.
- the breeding engine 112 selects target crosses from the sub-group, at 408, based on relatedness of the parents of the crosses within the subgroup.
- the relatedness of the parents is employed, by the breeding engine 112, to inhibit final selected crosses from being too closely related, i.e., to promote genetic diversity and/or to avoid risk of choosing a same parent among a substantial number of the final selected crosses.
- the parent may be selected for multiple of the crosses in the sub-group.
- the parent or its parents (broadly, the parental line) is/are flawed, the crosses including that parent may be disqualified from being a commercial product 108 in the system 100.
- the method 400 limits the potential impact of certain flawed parental lines in the breeding pipeline 102.
- the breeding engine 112 in connection with selecting the target crosses, the breeding engine 112 optionally (as indicated by the dotted lines in FIG. 4) clusters the parents, at 410, based on relatedness of the parents, through use of similarity markers. In so doing, for example, the breeding engine 112 characterizes a distance between two parents, where less similarity exists for two parents that are separated by a greater distance.
- the similarity markers are typically computed apart from the method 400 using raw marker data for the parents (as included in data structure 114, for example), with a simple matching coefficient as the similarity measure.
- corresponding markers in each parent may be compared, and the number of locations where they are similar, divided by the total number of markers, may provide a similarity coefficient (or marker) between two parents.
- a similarity coefficient or marker
- the breeding engine 1 12 may determine a distance metric for each potential cross, based on the relatedness of the parents, through use of Equations (2) and
- Equations (2) and (3) sy is the similarity between i and j parents, and ly is the i) th cross entry of the Laplacian matrix L.
- the breeding engine 1 12 employs spectral clustering, followed by Eigen Analysis, to
- the breeding engine 1 12 utilizes the Eigen Analysis to estimate the number of clusters in an unsupervised manner.
- Equation (4) L is the Laplacian matrix, created from the similarity distance s i; -, and L is the normalized Laplacian that is normalized by a diagonal matrix D.
- Eigen analysis of L provides the number of clusters.
- Equation (5) the normalized Laplacian matrix is decomposed using a singular value decomposition.
- the matrix, ⁇ contains the Eigen values that capture the number of the clusters of the data sets according to spectral clustering.
- the breeding engine 1 12 then clusters the parents using a K-Means algorithm.
- the K-Means algorithm is a stochastic or random clustering mechanism
- the breeding engine 1 12 may cluster the parents in multiple different realizations of the K-Means algorithm, selecting the maximum, or higher, inter cluster distance.
- spectral clustering is used herein, it should be appreciated that other clustering algorithms may be employed, at 410, including, for example, Hierarchical Clustering, Bayesian Clustering, C-means Clustering etc.
- L U ⁇ U T (5)
- the potential crosses are classified in generic clusters depending on the clusters to which its parents belong.
- the breeding engine 1 12 computes a performance score, which is based on commercial advancement of the parents and the data collected from commercial activity, testing, etc. of the parents.
- the cluster performance scores for the crosses i.e., progenyClusterScore, Cluster Scores
- FIG. 3E an example clustering of parents for potential crosses is illustrated in FIG.
- each parent is illustrated as a dot, including, specifically, parents 502a-c.
- the parents are clustered into two distinct clusters 504, 506.
- the performance score for the cross between parents 502a, 502b may be higher than the performance score for the cross between parents 502b, 502c, because they are part of different clusters and/or because 502c has more advancements than 502a.
- the breeding engine 1 12 selects the target crosses, based on whether or not the crosses (particularly their parents) satisfy a relatedness threshold, at 412.
- the breeding engine 1 12 filters the crosses based on the relatedness threshold, which is derived from a percentage of parents of the crosses belonging to individual clusters.
- the number of crosses to be selected, based on parents from each cluster, for example, is proportional to the size of the genetic cluster and the score of the cluster.
- the breeding engine 1 12 utilizes progeny cluster scores (the cluster scores computed using the data from the progeny produced from the given cluster), for example, column VV in excerpt 300, and cluster scores (the cluster scores computed using the data from the parents from a given cluster), for example, column WW in the excerpt 300, to filter ones of the potential crosses based on relatedness.
- progeny cluster scores and the cluster scores are normalized, to provide the same scale, and then combined by the breeding engine 112 in one or more manners such as, for example, addition, multiplication, etc.
- a number of crosses selected from each cluster may be proportional to the cluster score and/or size of the cluster.
- the parents are sorted within the cluster according to a performance metric (for example, "perfMetric" in column TT in excerpt 300) and the top crosses are selected (e.g., above the number of crosses "threshold,” etc.).
- Example pass/fail results are shown in the excerpt 300 in FIG. 3E in column XX (PASS CLUSTER FILTERING).
- the cross identified as L2/L1434 fails (i.e., the cross includes a "FALSE” notation in column XX of FIG. 3E) while the cross identified as L3/L1434 passes (i.e., the cross includes a "TRUE” notation in column XX of in FIG. 3E), even though both have the same cluster scores, based on the number of crosses selected and the relative perfMetric scores (column TT in excerpt 300).
- an even distribution of crosses in the clusters may or may not occur, as a different number of crosses can be selected from each, or some, of the clusters. For example, more crosses may be selected which include parents from clusters with higher cluster scores.
- a corresponding number of top crosses are selected from each of the clusters and sorted according to performance scores (e.g., the perfMetric score shown in column TT in excerpt 300, etc.). For example, in connection with the excerpt 300, after obtaining the cluster scores shown in columns VV-WW, the breeding engine 112 sorts the crosses within each genetic cluster according to the perfMetric score in column TT.
- example clusters include M_l_3, M_3_3 (Male Clusters), and F_2_2, F_l_2 (Female Clusters).
- the crosses are sorted by the breeding engine 112, and a number of the crosses are selected (e.g., based on relative ranking, etc.). As previously indicated, the number of crosses to be selected within each of the clusters may be, generally, linearly proportional to the size of the cluster and the average cluster scores. In general, it is contemplated that the clusters with higher average scores will contain higher genetic value.
- the breeding engine 1 12 filters the target crosses based on at least one rule, at 414, accessed from or retrieved from a rule data structure, for example, associated with the crosses data structure 1 14, etc.
- the rules may include any desired rules such as, for example, the rules described above in connection with Table 1, etc.
- the rules are generally standardized and are built based on the characteristics and/or traits of the parents, crosses, and/or their lines, and may be any criterion the breeder desires to use, including any genotype, phenotype, or any other trait or characteristic that can be used to describe and/or distinguish a plant or commercial crop product and/or their performance.
- Common example bases for rules include stalk strength, root strength, yield, disease tolerance, stress tolerance, cost of developing into a commercial product, cost of goods, test weight, plant height, ear height, as well as those criterion and/or technologies described in other sections herein for distinguishing tissues and/or performances.
- the breeding engine 1 12 may select parents (or potential crosses) (e.g., in connection with operation 414 in method 400, etc.), based on three rules: parent dropped, root strength, and stalk strength.
- parents or potential crosses
- root strength e.g., in connection with operation 414 in method 400, etc.
- stalk strength e.g., stalk strength
- the breeding engine 1 12 when a root strength rule is applied, for example, the breeding engine 1 12 will select only those crosses (and their parents) whose root strength scores are higher (or lower) than a threshold set by the breeder or other user; those crosses (and their parents) whose root strength scores do not meet or exceed the threshold (or vice-versa) are not selected for advancement onto commercialization. In certain other embodiments, this process can run through several iterations, until each cross has been evaluated against all the rules and/or performance thresholds and/or criteria that the breeder wishes to use to select the preferred crosses for advancement. With reference to FIG. 3E, column YY
- (PASS RULE FILTER) in the excerpt 300 represents the cumulative/iterative results of the breeding engine 1 12 (e.g., in connection with operation 414 of method 400, etc.) applying various rules (e.g., the three rules identified above, etc.) to an example data set for parents PI, P2.
- parents L 592, L 349, L 1460, and L 638, as designated in columns A, B, are indicated, in column YY, as satisfying all the thresholds set by the breeder (while all of the other parents/crosses do not).
- the breeding engine 112 optionally (as indicated by the dotted lines in FIG. 4) selects ones of the selected filtered crosses based on certain risks associated therewith.
- the breeding engine 112 may use a quadratic algorithm such as that represented by Equation (6) to find a set of desired parents to use, taking into account the risks and diversity associated with the selected set of parents.
- Equation (6) solves for an optimal set of parent distributions, which would be captured in the decision variable x.
- xi represents a proportion of the i th parent
- ci represents performance of the 1 th parent
- p y represents a performance index of the cross between the 1 th parent and j" 1 parent
- ry represents a risk index of the cross between the 1 th parent and j" 1 parent
- Sy represents similarity between the i th parent and j" 1 parent.
- per risk and X div are the weights for performance, risk, and diversity, respectively.
- Equation (6) the c T x + x T Px terms denote the performance; x T Rx is the risk (R is a matrix representation of the terms ⁇ 3 ⁇ 4 (the risk value computed in column VV in the excerpt 300, for example, between lines) and computed for each of the pair of possible parent combinations or crosses, as indicated below); and x T Sx is the similarity.
- the breeding engine 112 thus attempts to improve (if not maximize) performance, limit (if not minimize) risk, and limit (if not minimize) similarity, through Equation (6).
- the constraints in Equation (6) impose that x is a probability distribution, and balance the distribution by gender.
- the breeding engine 112 By solving the quadratic program described in Equation (6), the breeding engine 112 generally inhibits use of parents with similar genetic backgrounds, thereby accounting for (and, potentially, improving) population diversity.
- FIG. 7 is a hypothetical graphical representation 700 of a distribution of parental usage in a breeding system, which provides an illustration of the effect of considering the diversity term in Equation (6) (i.e., A div x T Sx), as compared to not incorporating and/or considering the term.
- a first set of bars 702 shows a hypothetical distribution of parents for a population of crosses based on conventional methods (i.e., in the absence of consideration of diversity), while a second set of bars 704 shows a hypothetical redistribution of the parents for a population of crosses as potentially achieved by the systems and methods herein (i.e., a hypothetical consideration of diversity).
- the representation of FIG. 7 is merely provided for purposes of illustration and should not be consider a limitation of the disclosure herein or an indication of a required and/or consistent impact of the methods herein relative to conventional methods.
- the breeding engine 112 may, optionally, optimize (broadly, filter) the population of crosses by determining whether the parents, and/or the crosses, are associated with certain particular risks.
- the particular risks of interest for each individual parent include five risks that may be modeled, as represented by Equations (7)- (11) below, by fitting an exponential curve parameterized by the age of the parental line, the number of times the parental line is tested, and the standard deviation of the root and stalk lodging (all, broadly, risks).
- Equation (7) represents a risk based on age (e.g., relatively older lines would be associated with generally less risk given their longevity in the breeding pipeline 102, etc.) (reliant on columns AA and BB from excerpt 300);
- Equation (8) represents a risk based on number of times a hybrid is tested (e.g., the risk of using certain parental lines based on a number of times the lines have been subjected to testing in the breeding pipeline 102, etc.) (reliant on column EE from excerpt 300, which in turn is the sum of columns CC and DD (which are the numbers of tested hybrids for the parents));
- Equation (9) represents a risk based on using lines with a higher root lodging (reliant on column FF from excerpt 300);
- Equation (10) represents a risk based on using lines with a higher stalk lodging (reliant on Column GG from excerpt 300);
- Equation (11) represents a risk based on Goss Wilt susceptibility(reliant on Column HH from excerpt 300).
- Equations (7)-(l 1) i. e., a x , a 2 , 0C3 , ⁇ ⁇ , 3 ⁇ 4 ⁇ ? 3 ). It should be appreciated, however, that risk may be accounted for via a variety of different methods known to those skilled in the art, and used herein as desired. In addition, while Equations (7)-(l 1) are generally directed toward risks associated with maize, it should be appreciated that risk for other plants may be account for as desired ⁇ e.g. , via other methods, etc.).
- Table 2 illustrates hypothetical average risk values for parents in connection with age, a number of times tested, root lodging, stalk lodging, and Goss Wilt. In particular, Table 2 illustrates how various attributes may be influenced by accounting for risk.
- the first column in Table 2 identifies various attributes.
- the second column illustrates the average risk values, for the given particular attribute, with modeling, as calculated using Equations (7)-(l 1).
- the third column illustrates the average risk values as calculated without modeling.
- the risk values for the average yield BLUP of the parents selected in Table 2 may be better when the above modeling was not applied; as shown, the risk values for root lodging, stalk lodging and Goss Wilt are better when the modeling was not applied.
- risk values for age and number of times tested for the parents selected based on the above modeling indicates that the parents have been tested more often and have spent a longer time in a corresponding breeding pipeline of the system.
- the selected parents via modeling, may have some lower average risk scores for certain attributes, but are selected nevertheless because of their demonstrated history of being selected and used in the breeding pipeline, thereby potentially reducing the overall risk associated with using them.
- the risk computation takes into account the several attributes associated with crosses (e.g., age, a number of times tested, root lodging, stalk lodging, and Goss Wilt in Table 2; standability; pathological characteristics; etc.). In so doing, the risk
- Equation (6) and the "Average Risk Value without Modeling" shows the possible values if the risk modeling is omitted.
- the two scenarios provide a demonstration that, in the absences of risk modeling, while attempting to increase and/or maximize performance (such as for Root Lodging, Stalk Lodging, and Goss Wilt), the selected population may fail to reach desired values for several attributes like age of the parents and a number of times the parents are tested, etc.
- the risk computation described herein thus inhibits the selection of crosses having undesirable values for such attributes, despite potentially having high yield characteristics, for example.
- the cross level risk ry is then used to construct a cross level risk matrix, for example, matrix R in Equation (6), to thereby facilitate completion of operation 416.
- r r age + r N + r RTLP + r STLP + r GW (12)
- Equation (13) the breeding engine 112 employs Equation (13) to determine which set of crosses should be selected using the parents that were obtained through Equation (6).
- ⁇ is the weight for diversity
- S ⁇ is the incidence matrix from crosses to the parents (including 0's and l 's)
- x opt is the parent distribution calculated from Equation (6)
- c is the population prediction score that the breeding engine 112 computes employing Equation (1) (or other method described herein used to determine a performance index of crosses, and which relies on the BLUP of their traits, the number of commercial products in which the parents have been used, the similarity between the parents, marker data of the parents, and the scores assigned to the parental lines by the models that predicts the probability of the parents advancing through the breeding pipeline), and z is the origin selection decision vector.
- z 0PT arg max c T z - A
- the matrix S RM maps the origins to the Relative Maturity (RM) groups, and as a consequence, S RM z is the projection of usage of parents from different relative maturities.
- the vectors P RM Max and P RM Min restrict the minimum and maximum parent usage from various RM groupings.
- P GENDER Max maintain similar balance for gender or heterotic groups
- S Trait , P Trait Max, and P Trait Min assist in maintaining various desired portfolios of traits.
- other constraints relating to frequency of a certain QTL or traits, and the desired product portfolio may also (or alternatively) be included in a similar manner, for example, by constructing appropriate projection matrices.
- an iterative process of the above operations may be applied to successively narrow down the possible options of parents (e.g., as represented by the five layers of optimization indicated in FIGS. 3E-3F, at columns ZZ-DDD), for example, by initially selecting a relatively large first set of potential crosses, then applying the models described above to account for genetic diversity and/or risks to select a smaller second set from the first, then reapplying the models to select an even smaller third set of crosses from the second set, and so on until the number of crosses has been sufficiently narrowed, as desired (e.g., five times as indicated in the excerpt 300, etc.).
- Equation (12) the score matrices P and R defined in Equation (6) and the score vector c defined in Equation (13) can be normalized using Equations (14), (15) and (16) below.
- the breeding engine 1 12 directs the selected parents, and their potential crosses, at 418, to the plant breeding pipeline 102, and in particular, to the initial grow phase 104.
- selection would be based on the results of the fifth optimization layer, indicated in column DDD of FIG. 3F.
- none of the crosses would be selected as all included a "FALSE" designation (with a further explanation for the "FALSE” designation then provided in column EEE).
- a breeder typically relies on a variety of parameters of the parents to filter ones of the potential crosses, ultimately coming to a number of seed origins (or parents), which are provided to a breeding pipeline (e.g., breeding pipeline 102, etc.).
- a breeding pipeline e.g., breeding pipeline 102, etc.
- 120 potential crosses may have been available for selection to breeders via conventional methods, from available historical data about the parents, to enter a breeding pipeline over each of several recent years, whereby additional resources were then spent processing, testing, and cultivating each of the 120 crosses to arrive at a subset of crosses that were advanced to become commercial products.
- the breeding engine 1 12 described herein Through use of the breeding engine 1 12 described herein, of the 120 potential crosses, 24 were identified and selected (e.g. , at 416 in the method 400, etc.) to enter the breeding pipeline. In so doing, the 24 crosses included approximately 69% of the commercially successful crosses that had been selected by the breeder, historically, using conventional techniques, thus providing a substantial efficiency gain (i.e., 24 crosses instead of 120 crosses entering the breeding pipeline).
- the systems and methods herein employ the commercial success history of parents (and parental lines), in combination with historic trait information, to select seed origins to be introduced to a breeding pipeline. The reliance on multiple different types of data, including the commercial success, the relatedness of the parents, and risk provides a more complete picture of how the seed origins will progress in the breeding pipeline.
- breeders can vastly improve their pipelines to identify and select for advancement those hybrids that would otherwise be potentially eliminated when using traditional operations.
- the systems and methods herein are not limited geographically, or otherwise, in any way.
- the breeding engine herein can be used to recommend an optimal set of crosses to make for that specific market/environment by weighting the data corresponding to certain traits that affect crop performance and/or commercial/market success in that environment.
- Such environment may be represented globally or regionally, or it may be as granular as a specific location within a filed (such that the same field is identified to have different such environments).
- the breeding engine herein may be used to target the development of products specific to certain markets, geographies, soil types, etc., or with directives to, maximize profits, maximize customer satisfaction, minimize production costs, etc.
- diagram 804 provides an indication of all the potential crosses of the four parents 802, where a cross is indicated by each connecting line.
- the matrix 806 further includes certain data related to the parents and/or crosses, similar to the data included in excerpt 300, such as, for example, an expected yield for each of the crosses and also an age for each of the crosses, which is indicative of the average age of the parents 802.
- the matrix 806 further includes a "SIM,” or genetic similarity of the parents 802.
- Exemplary numbers indicate the probabilities of selecting the "best” crosses to be included in the breeding pipeline. Specifically, the number of potential crosses for a given set of parents is provided by Equation (17) below: n(n-l)
- N 6 (as indicated in FIG. 8).
- n may be 1000, while r is 100.
- the total potential number of parents would be approximately 10 400 .
- the probability of reaching the optimal cohorts given the variables, by human selection or conventional methodologies (e.g., without considering genetic diversity, commercial success, etc.), for example, would be 10 3 / 10 400 or 1 / 10 297 .
- the systems and methods herein may account for the entire set of potential crosses (in the context of the variables described herein), and therefore would not artificially reduce the set of the potential crosses as potentially made necessary by the computational complexity and/or resources available.
- the systems and methods herein may provide improvement over conventional methods by providing for population level distribution of parental usage (e.g., genetic diversity, etc.).
- parental usage e.g., genetic diversity, etc.
- IUI inbred usage index
- an IUI of 100% would imply that every parent (in the set of potential crosses) is used only once when selecting the filtered target crosses, as described above, or otherwise (e.g., via conventional manual methods, etc.).
- a lower IUI would indicate that one parent or multiple parents are more prevalent (i.e., the lower the IUI, the higher the occurrence of a parent in the selected potential crosses (destined for the breeding pipeline 102, for example)).
- historical data for a conventional breeding method yields the IUI values represented at 902 (IUI value of about 18.86) and 904 (IUI value of about 15.29), for years YYYY and YYYY +1 (one year later), respectively.
- the selected filtered target potential crosses would provide the IUI at each of 906 (IUI value of about 31.38) and 908 (IUI value of about 29.72), for the respective years. That is, at least in the context of this example, the IUI for selected filtered target crosses is greater than 20, greater than 25, and/or greater than 30, or other suitable values, etc. As shown, the population level distribution of parental usage is increased substantially over manual conventional breeding methods.
- the functions described herein may be described in computer executable instructions stored on a computer readable media, and executable by one or more processors.
- the computer readable media is a non-transitory computer readable media.
- such computer readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Combinations of the above should also be included within the scope of computer-readable media.
- the above- described embodiments of the disclosure may be implemented using computer programming or engineering techniques including computer software, firmware, hardware or any combination or subset thereof, wherein the technical effect may be achieved by performing at least one of the following operations: (a) accessing a data structure representative of multiple parents; (b) identifying a set of potential crosses, each potential cross in the set of potential crosses including at least two of the multiple parents included in the data structure; (c)selecting, by at least one computing device, a subgroup of potential crosses, from the set of potential crosses, based on one or more thresholds associated with population prediction scores for the set of potential crosses, each population prediction score associated with a prediction of commercial success for the associated potential cross within the set of potential crosses; (d) selecting, by the at least one computing device, multiple target crosses from the subgroup of potential crosses based on a genetic relatedness of the parents in the subgroup of potential crosses; € filtering, by the at least one computing device, the target crosses based on at least one rule
- Example embodiments are provided so that this disclosure will be thorough, and will fully convey the scope to those who are skilled in the art. Numerous specific details are set forth such as examples of specific components, devices, and methods, to provide a thorough understanding of embodiments of the present disclosure. It will be apparent to those skilled in the art that specific details need not be employed, that example embodiments may be embodied in many different forms and that neither should be construed to limit the scope of the disclosure. In some example embodiments, well-known processes, well-known device structures, and well- known technologies are not described in detail. In addition, advantages and improvements that may be achieved with one or more exemplary embodiments disclosed herein may provide all or none of the above mentioned advantages and improvements and still fall within the scope of the present disclosure.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Genetics & Genomics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Botany (AREA)
- Developmental Biology & Embryology (AREA)
- Environmental Sciences (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Breeding Of Plants And Reproduction By Means Of Culturing (AREA)
- Chemical & Material Sciences (AREA)
- Hematology (AREA)
- Medicinal Chemistry (AREA)
- Image Analysis (AREA)
- Molecular Biology (AREA)
- Urology & Nephrology (AREA)
- Pretreatment Of Seeds And Plants (AREA)
- Food Science & Technology (AREA)
- Biomedical Technology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
Abstract
Description
Claims
Priority Applications (8)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP17811038.3A EP3468349A4 (en) | 2016-06-08 | 2017-06-08 | Methods for identifying crosses for use in plant breeding |
MX2018015256A MX2018015256A (en) | 2016-06-08 | 2017-06-08 | Methods for identifying crosses for use in plant breeding. |
BR112018075333-5A BR112018075333A2 (en) | 2016-06-08 | 2017-06-08 | Intersection identification methods for use in breeding plants, systems and storage media |
CA3026265A CA3026265A1 (en) | 2016-06-08 | 2017-06-08 | Methods for identifying crosses for use in plant breeding |
CN201780035726.0A CN109328016A (en) | 2016-06-08 | 2017-06-08 | Method for the hybrid species of plant breeding for identification |
AU2017277808A AU2017277808A1 (en) | 2016-06-08 | 2017-06-08 | Methods for identifying crosses for use in plant breeding |
PH12018502562A PH12018502562A1 (en) | 2016-06-08 | 2018-12-05 | Methods for identifying crosses for use in plant breeding |
AU2023226776A AU2023226776A1 (en) | 2016-06-08 | 2023-09-08 | Methods for identifying crosses for use in plant breeding |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201662347344P | 2016-06-08 | 2016-06-08 | |
US62/347,344 | 2016-06-08 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017214445A1 true WO2017214445A1 (en) | 2017-12-14 |
Family
ID=60572063
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2017/036626 WO2017214445A1 (en) | 2016-06-08 | 2017-06-08 | Methods for identifying crosses for use in plant breeding |
Country Status (9)
Country | Link |
---|---|
US (3) | US10327400B2 (en) |
EP (1) | EP3468349A4 (en) |
CN (1) | CN109328016A (en) |
AU (2) | AU2017277808A1 (en) |
BR (1) | BR112018075333A2 (en) |
CA (1) | CA3026265A1 (en) |
MX (1) | MX2018015256A (en) |
PH (1) | PH12018502562A1 (en) |
WO (1) | WO2017214445A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3871160A4 (en) * | 2018-10-24 | 2022-07-27 | Climate LLC | Leveraging genetics and feature engineering to boost placement predictability for seed product selection and recommendation by field |
US11568467B2 (en) | 2019-04-10 | 2023-01-31 | Climate Llc | Leveraging feature engineering to boost placement predictability for seed product selection and recommendation by field |
US11576316B2 (en) | 2019-03-28 | 2023-02-14 | Monsanto Technology Llc | Methods and systems for use in implementing resources in plant breeding |
US11627710B2 (en) | 2017-12-10 | 2023-04-18 | Monsanto Technology Llc | Methods and systems for identifying hybrids for use in plant breeding |
US11632920B2 (en) | 2016-06-08 | 2023-04-25 | Monsanto Technology Llc | Methods for identifying crosses for use in plant breeding |
US11728010B2 (en) | 2017-12-10 | 2023-08-15 | Monsanto Technology Llc | Methods and systems for identifying progenies for use in plant breeding |
US11810645B1 (en) | 2022-07-14 | 2023-11-07 | Cannamatrix Inc. | System and method of making predictions of mature cannabis plants from seedling information |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11568340B2 (en) * | 2017-11-09 | 2023-01-31 | Climate Llc | Hybrid seed selection and seed portfolio optimization by field |
CN108346107B (en) * | 2017-12-28 | 2020-11-10 | 创新先进技术有限公司 | Social content risk identification method, device and equipment |
US20220174900A1 (en) * | 2019-03-28 | 2022-06-09 | Monsanto Technology Llc | Methods And Systems For Use In Implementing Resources In Plant Breeding |
WO2021072165A1 (en) * | 2019-10-10 | 2021-04-15 | Pioneer Hi-Bred International, Inc. | Synchronized breeding and agronomic methods to improve crop plants |
CN111312335B (en) * | 2020-02-24 | 2023-07-21 | 吉林省农业科学院 | Soybean parent selection method and device, storage medium and electronic equipment |
WO2022066540A1 (en) * | 2020-09-24 | 2022-03-31 | Monsanto Technology Llc | Systems and methods relating to protocols in plant breeding pipelines |
CN112349351B (en) * | 2020-11-10 | 2022-10-11 | 邯郸市农业科学院 | Method for breeding ultra-early-maturing cotton germplasm with assistance of molecular markers |
AU2021391547A1 (en) * | 2020-12-02 | 2023-06-22 | Monsanto Technology Llc | Methods and systems for automatically tuning weights associated with breeding models |
JPWO2023042283A1 (en) * | 2021-09-15 | 2023-03-23 | ||
CN113930538B (en) * | 2021-11-02 | 2024-01-23 | 华南农业大学 | Kit for identifying rice seed-suitable region, prediction method thereof and construction of prediction model |
JPWO2023089775A1 (en) * | 2021-11-19 | 2023-05-25 | ||
WO2023129746A1 (en) * | 2021-12-31 | 2023-07-06 | Benson Hill, Inc. | Systems and methods for selecting recommended crosses with increased an probability of meeting plant-based product specifications |
CN116076353A (en) * | 2022-11-28 | 2023-05-09 | 北京中农斯达农业科技开发有限公司 | Anthocyanin-rich purple corn breeding system and method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050144664A1 (en) * | 2003-05-28 | 2005-06-30 | Pioneer Hi-Bred International, Inc. | Plant breeding method |
US20100100980A1 (en) * | 2005-05-27 | 2010-04-22 | Monsanto Technology Llc | Methods and Compositions to Enhance Plant Breeding |
WO2013026085A1 (en) * | 2011-08-23 | 2013-02-28 | The University Of Queensland | Disease resistant plant breeding method |
US20130117878A1 (en) | 2008-10-02 | 2013-05-09 | Pioneer Hi-Bred International, Inc. | Statistical approach for optimal use of genetic information collected on historical pedigrees |
US20140130200A1 (en) * | 2007-08-30 | 2014-05-08 | Seminis Vegetable Seeds, Inc. | Forward breeding |
WO2016022517A1 (en) * | 2014-08-08 | 2016-02-11 | Pioneer Hi-Bred International, Inc. | Compositions and methods for identifying and selecting maize plants with resistance to northern leaf blight |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7269587B1 (en) | 1997-01-10 | 2007-09-11 | The Board Of Trustees Of The Leland Stanford Junior University | Scoring documents in a linked database |
US6285999B1 (en) | 1997-01-10 | 2001-09-04 | The Board Of Trustees Of The Leland Stanford Junior University | Method for node ranking in a linked database |
EP2360472B1 (en) | 2003-12-17 | 2015-04-15 | Fred Hutchinson Cancer Research Center | Methods and materials for canine breed identification |
US20070083456A1 (en) | 2004-08-10 | 2007-04-12 | Akers Wayne S | Algorithmic trading |
EP1962212A1 (en) | 2007-01-17 | 2008-08-27 | Syngeta Participations AG | Process for selecting individuals and designing a breeding program |
US8645417B2 (en) | 2008-06-18 | 2014-02-04 | Microsoft Corporation | Name search using a ranking function |
US8290926B2 (en) * | 2010-01-21 | 2012-10-16 | Microsoft Corporation | Scalable topical aggregation of data feeds |
WO2012075125A1 (en) * | 2010-11-30 | 2012-06-07 | Syngenta Participations Ag | Methods for increasing genetic gain in a breeding population |
CN104838263B (en) | 2012-06-15 | 2017-12-05 | 农业基因遗传学有限公司 | The method of set of landmarks is penetrated into for Select gene |
US9727926B2 (en) | 2014-03-03 | 2017-08-08 | Google Inc. | Entity page recommendation based on post content |
US9734239B2 (en) | 2014-06-30 | 2017-08-15 | International Business Machines Corporation | Prompting subject matter experts for additional detail based on historical answer ratings |
WO2016025848A1 (en) | 2014-08-15 | 2016-02-18 | Monsanto Technology Llc | Apparatus and methods for in-field data collection and sampling |
WO2016044050A1 (en) | 2014-09-16 | 2016-03-24 | Monsanto Technology Llc | Improved methods of plant breeding using high-throughput seed sorting |
CA3026265A1 (en) | 2016-06-08 | 2017-12-14 | Monsanto Technology Llc | Methods for identifying crosses for use in plant breeding |
AU2018380430A1 (en) | 2017-12-10 | 2020-06-18 | Monsanto Technology Llc | Methods and systems for identifying hybrids for use in plant breeding |
BR112020011321A2 (en) | 2017-12-10 | 2020-11-17 | Monsanto Technology Llc | methods and systems for identifying progenies for use in plant breeding |
-
2017
- 2017-06-08 CA CA3026265A patent/CA3026265A1/en active Pending
- 2017-06-08 CN CN201780035726.0A patent/CN109328016A/en active Pending
- 2017-06-08 US US15/618,023 patent/US10327400B2/en active Active
- 2017-06-08 BR BR112018075333-5A patent/BR112018075333A2/en active Search and Examination
- 2017-06-08 EP EP17811038.3A patent/EP3468349A4/en active Pending
- 2017-06-08 AU AU2017277808A patent/AU2017277808A1/en not_active Abandoned
- 2017-06-08 MX MX2018015256A patent/MX2018015256A/en unknown
- 2017-06-08 WO PCT/US2017/036626 patent/WO2017214445A1/en unknown
-
2018
- 2018-12-05 PH PH12018502562A patent/PH12018502562A1/en unknown
-
2019
- 2019-06-21 US US16/448,334 patent/US11632920B2/en active Active
-
2023
- 2023-04-24 US US18/138,716 patent/US20230255155A1/en active Pending
- 2023-09-08 AU AU2023226776A patent/AU2023226776A1/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050144664A1 (en) * | 2003-05-28 | 2005-06-30 | Pioneer Hi-Bred International, Inc. | Plant breeding method |
US20100100980A1 (en) * | 2005-05-27 | 2010-04-22 | Monsanto Technology Llc | Methods and Compositions to Enhance Plant Breeding |
US20140130200A1 (en) * | 2007-08-30 | 2014-05-08 | Seminis Vegetable Seeds, Inc. | Forward breeding |
US20130117878A1 (en) | 2008-10-02 | 2013-05-09 | Pioneer Hi-Bred International, Inc. | Statistical approach for optimal use of genetic information collected on historical pedigrees |
WO2013026085A1 (en) * | 2011-08-23 | 2013-02-28 | The University Of Queensland | Disease resistant plant breeding method |
WO2016022517A1 (en) * | 2014-08-08 | 2016-02-11 | Pioneer Hi-Bred International, Inc. | Compositions and methods for identifying and selecting maize plants with resistance to northern leaf blight |
Non-Patent Citations (3)
Title |
---|
KEVIN P. MURPHY: "Machine learning: a probabilistic perspective", 2012, MIT PRESS |
OPITZMACLIN: "Popular ensemble methods: An empirical study", JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, vol. 11, 1999, pages 169 - 98 |
ROKACH: "Ensemble-based classifiers", ARTIFICIAL INTELLIGENCE REVIEW, vol. 33, no. 1-2, 2010, pages 1 - 39, XP019766150 |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11632920B2 (en) | 2016-06-08 | 2023-04-25 | Monsanto Technology Llc | Methods for identifying crosses for use in plant breeding |
US11627710B2 (en) | 2017-12-10 | 2023-04-18 | Monsanto Technology Llc | Methods and systems for identifying hybrids for use in plant breeding |
US11728010B2 (en) | 2017-12-10 | 2023-08-15 | Monsanto Technology Llc | Methods and systems for identifying progenies for use in plant breeding |
EP3871160A4 (en) * | 2018-10-24 | 2022-07-27 | Climate LLC | Leveraging genetics and feature engineering to boost placement predictability for seed product selection and recommendation by field |
US11593674B2 (en) | 2018-10-24 | 2023-02-28 | Climate Llc | Leveraging genetics and feature engineering to boost placement predictability for seed product selection and recommendation by field |
US12039463B2 (en) | 2018-10-24 | 2024-07-16 | Climate Llc | Leveraging genetics and feature engineering to boost placement predictability for seed product selection and recommendation by field |
US11576316B2 (en) | 2019-03-28 | 2023-02-14 | Monsanto Technology Llc | Methods and systems for use in implementing resources in plant breeding |
US11568467B2 (en) | 2019-04-10 | 2023-01-31 | Climate Llc | Leveraging feature engineering to boost placement predictability for seed product selection and recommendation by field |
US11810645B1 (en) | 2022-07-14 | 2023-11-07 | Cannamatrix Inc. | System and method of making predictions of mature cannabis plants from seedling information |
US20240105278A1 (en) * | 2022-07-14 | 2024-03-28 | Cannamatrix Inc. | System and method of making predictions of mature cannabis plants from seedling information |
Also Published As
Publication number | Publication date |
---|---|
US10327400B2 (en) | 2019-06-25 |
BR112018075333A2 (en) | 2019-03-19 |
US11632920B2 (en) | 2023-04-25 |
US20170354105A1 (en) | 2017-12-14 |
CN109328016A (en) | 2019-02-12 |
CA3026265A1 (en) | 2017-12-14 |
PH12018502562A1 (en) | 2019-09-30 |
EP3468349A4 (en) | 2020-01-29 |
AU2023226776A1 (en) | 2023-09-28 |
US20230255155A1 (en) | 2023-08-17 |
MX2018015256A (en) | 2019-04-25 |
AU2017277808A1 (en) | 2018-12-20 |
EP3468349A1 (en) | 2019-04-17 |
US20190313591A1 (en) | 2019-10-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230255155A1 (en) | Methods For Identifying Crosses For Use In Plant Breeding | |
US11728010B2 (en) | Methods and systems for identifying progenies for use in plant breeding | |
Ortiz et al. | High yield potential, shuttle breeding, genetic diversity, and a new international wheat improvement strategy | |
US20230247953A1 (en) | Methods And Systems For Identifying Hybrids For Use In Plant Breeding | |
Mubai et al. | Phenotypic correlation, path coefficient and multivariate analysis for yield and yield-associated traits in groundnut accessions | |
US20230180688A1 (en) | Methods and systems for use in implementing resources in plant breeding | |
Ahmadi et al. | Rethinking plant breeding | |
Lin et al. | Genomic prediction for grain yield in a barley breeding program using genotype× environment interaction clusters | |
US20230301257A1 (en) | Methods And Systems For Use In Implementing Resources In Plant Breeding | |
US20220174900A1 (en) | Methods And Systems For Use In Implementing Resources In Plant Breeding | |
Paget et al. | Appraisal of test location and variety performance for the selection of tuber yield in a potato breeding program | |
US20230165204A1 (en) | Methods and systems for using envirotype in genomic selection | |
Falk | Phenotypic and molecular characterization root system architecture in diverse soybean (Glycine max L. Merr.) accessions | |
Dlamini | Genotype by environment interaction and resource optimization in sugarcane variety evaluation in Swaziland | |
Hunt | A Data Processing, Feature Engineering, Variable Selection, and Machine Learning Modeling Framework for Predictive Agriculture | |
WO2024182281A1 (en) | Methods and systems for use in defining advancement of seed products in breeding | |
Lee et al. | Genomic selection for crop improvement in fruits and vegetables: a systematic scoping review |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17811038 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 3026265 Country of ref document: CA |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112018075333 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 2017277808 Country of ref document: AU Date of ref document: 20170608 Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2017811038 Country of ref document: EP Effective date: 20190108 |
|
ENP | Entry into the national phase |
Ref document number: 112018075333 Country of ref document: BR Kind code of ref document: A2 Effective date: 20181206 |